# Voice

> Queue text, choose voices, and control playback.

Documentation: https://lattices.dev/voice/docs

**First check**

Voice owns spoken output: the queue, voices, and playback. Listening and spoken commands are Lattices voice commands.

Agent guide: [For agents](https://lattices.dev/voice/docs/agents/index.md).

First check (read-only): `lats voice status --json`
Expect: A `helper` section with the Voice.app queue, or an error code with a recovery step. This check makes no sound.

## Current documentation

- [Overview](https://lattices.dev/voice/docs/overview.md): Voice queues and plays spoken updates from agents and scripts. Its macOS app, Voice.app, is a separate process from Lattices.
- [Quickstart](https://lattices.dev/voice/docs/quickstart.md): Install Voice.app, confirm that Lattices can reach it, and speak a first line.
- [For agents](https://lattices.dev/voice/docs/agents/index.md): How an agent should give spoken updates through Voice, check that Voice.app is reachable, and stay inside the output boundary.
- [CLI](https://lattices.dev/voice/docs/cli.md): The lats voice commands that reach Voice, how the Lattices daemon forwards them to Voice.app, and what each playback command does.
- [API](https://lattices.dev/voice/docs/api.md): The speech.* WebSocket RPC that Voice.app serves over private speech.sock, its capability token, and the Lattices voice.* gateway.

## Retrieval

- [Public agent instructions](https://lattices.dev/voice/docs/AGENTS.md)
- [Full context](https://lattices.dev/voice/docs/llms-full.txt)
- [Structured documentation](https://lattices.dev/voice/docs/agent-docs.json)
- [All products](https://lattices.dev/llms.txt)